Training in progress, step 15500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31882bb59ace60deee154374a27b2586376c58b53c75d49fe8ef4f59d2735ff5
+oid sha256:9087679e21c72a03308c1f1042fa388a26aa895e37052d6ba8f2760f8ed9d62c
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82e4b1cf021ca896eccee4933476e879cc09f7c7ffd7042ea35f89be59ff4e77
+oid sha256:179ba7759c2da654ccc0155ea7d3cd89eacd0e0a80f00b4769a3bda069f1542b
 size 876185978

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0d6edc6d5302a8346a12d9e6fe0565676124247fff5bdb99ce34f828f59ad4
+oid sha256:71854c462585f75923baf32808b59ce1d40f6f83c6c3ee96dd1e08a419477550
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e3306facb62f6002f7c25d4399b0fe1fa4166d62925b311563b72ad9931d0b9
+oid sha256:02efed2160d416430cfdc4b1c07b94736d779e3a16a8f0c18ef61810e8e70171
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.47014790773391724,
   "best_model_checkpoint": "results/checkpoint-14000",
-  "epoch": 0.9978712080894092,
+  "epoch": 1.0311335816923897,
   "eval_steps": 500,
-  "global_step": 15000,
+  "global_step": 15500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -457,6 +457,21 @@
       "eval_samples_per_second": 233.634,
       "eval_steps_per_second": 3.662,
       "step": 15000
+    },
+    {
+      "epoch": 1.0311335816923897,
+      "grad_norm": 5.288357257843018,
+      "learning_rate": 3.281444030512684e-05,
+      "loss": 0.3673,
+      "step": 15500
+    },
+    {
+      "epoch": 1.0311335816923897,
+      "eval_loss": 0.47548824548721313,
+      "eval_runtime": 40.9898,
+      "eval_samples_per_second": 253.722,
+      "eval_steps_per_second": 3.977,
+      "step": 15500
     }
   ],
   "logging_steps": 500,
@@ -476,7 +491,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2632052105216e+17,
+  "total_flos": 1.305248890611794e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null